Method and System Providing Service Based on User Voice

3. The method for providing a service based on a user's voice according to claim 1, further comprising providing by the artificial neural network unit a feedback on analyzing the disposition of the first user and selecting the second user based on at least one of rating information input after a call between the first user and a second user, call time information, whether a call has been extended, frequency of appearance of a specific word during a call and whether a fee has been paid.

4. The method for providing a service based on a user's voice according to claim 1, wherein the speech emotion recognition model based on CNN uses at least one of Mel-spectrogram, MFCC, Roll off and Centroid as a feature value.